file_table.c

Go to the documentation of this file.

/*
 *  linux/fs/file_table.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 1997 David S. Miller ([email protected])
 */

#include <linux/string.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/eventpoll.h>
#include <linux/rcupdate.h>
#include <linux/mount.h>
#include <linux/capability.h>
#include <linux/cdev.h>
#include <linux/fsnotify.h>
#include <linux/sysctl.h>
#include <linux/lglock.h>
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/task_work.h>
#include <linux/ima.h>

#include <linux/atomic.h>

#include "internal.h"

/* sysctl tunables... */
struct files_stat_struct files_stat = {
    .max_files = NR_FILE
};

DEFINE_STATIC_LGLOCK(files_lglock);

/* SLAB cache for file structures */
static struct kmem_cache *filp_cachep __read_mostly;

static struct percpu_counter nr_files __cacheline_aligned_in_smp;

static void file_free_rcu(struct rcu_head *head)
{
    struct file *f = container_of(head, struct file, f_u.fu_rcuhead);

    put_cred(f->f_cred);
    kmem_cache_free(filp_cachep, f);
}

static inline void file_free(struct file *f)
{
    percpu_counter_dec(&nr_files);
    file_check_state(f);
    call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
}

/*
 * Return the total number of open files in the system
 */
static long get_nr_files(void)
{
    return percpu_counter_read_positive(&nr_files);
}

/*
 * Return the maximum number of open files in the system
 */
unsigned long get_max_files(void)
{
    return files_stat.max_files;
}
EXPORT_SYMBOL_GPL(get_max_files);

/*
 * Handle nr_files sysctl
 */
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
int proc_nr_files(ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
{
    files_stat.nr_files = get_nr_files();
    return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#else
int proc_nr_files(ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
{
    return -ENOSYS;
}
#endif

/* Find an unused file structure and return a pointer to it.
 * Returns NULL, if there are no more free file structures or
 * we run out of memory.
 *
 * Be very careful using this.  You are responsible for
 * getting write access to any mount that you might assign
 * to this filp, if it is opened for write.  If this is not
 * done, you will imbalance int the mount's writer count
 * and a warning at __fput() time.
 */
struct file *get_empty_filp(void)
{
    const struct cred *cred = current_cred();
    static long old_max;
    struct file * f;

    /*
     * Privileged users can go above max_files
     */
    if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) {
        /*
         * percpu_counters are inaccurate.  Do an expensive check before
         * we go and fail.
         */
        if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files)
            goto over;
    }

    f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
    if (f == NULL)
        goto fail;

    percpu_counter_inc(&nr_files);
    f->f_cred = get_cred(cred);
    if (security_file_alloc(f))
        goto fail_sec;

    INIT_LIST_HEAD(&f->f_u.fu_list);
    atomic_long_set(&f->f_count, 1);
    rwlock_init(&f->f_owner.lock);
    spin_lock_init(&f->f_lock);
    eventpoll_init_file(f);
    /* f->f_version: 0 */
    return f;

over:
    /* Ran out of filps - report that */
    if (get_nr_files() > old_max) {
        pr_info("VFS: file-max limit %lu reached\n", get_max_files());
        old_max = get_nr_files();
    }
    goto fail;

fail_sec:
    file_free(f);
fail:
    return NULL;
}

struct file *alloc_file(struct path *path, fmode_t mode,
        const struct file_operations *fop)
{
    struct file *file;

    file = get_empty_filp();
    if (!file)
        return NULL;

    file->f_path = *path;
    file->f_mapping = path->dentry->d_inode->i_mapping;
    file->f_mode = mode;
    file->f_op = fop;

    /*
     * These mounts don't really matter in practice
     * for r/o bind mounts.  They aren't userspace-
     * visible.  We do this for consistency, and so
     * that we can do debugging checks at __fput()
     */
    if ((mode & FMODE_WRITE) && !special_file(path->dentry->d_inode->i_mode)) {
        file_take_write(file);
        WARN_ON(mnt_clone_write(path->mnt));
    }
    if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
        i_readcount_inc(path->dentry->d_inode);
    return file;
}
EXPORT_SYMBOL(alloc_file);

static void drop_file_write_access(struct file *file)
{
    struct vfsmount *mnt = file->f_path.mnt;
    struct dentry *dentry = file->f_path.dentry;
    struct inode *inode = dentry->d_inode;

    put_write_access(inode);

    if (special_file(inode->i_mode))
        return;
    if (file_check_writeable(file) != 0)
        return;
    __mnt_drop_write(mnt);
    file_release_write(file);
}

/* the real guts of fput() - releasing the last reference to file
 */
static void __fput(struct file *file)
{
    struct dentry *dentry = file->f_path.dentry;
    struct vfsmount *mnt = file->f_path.mnt;
    struct inode *inode = dentry->d_inode;

    might_sleep();

    fsnotify_close(file);
    /*
     * The function eventpoll_release() should be the first called
     * in the file cleanup chain.
     */
    eventpoll_release(file);
    locks_remove_flock(file);

    if (unlikely(file->f_flags & FASYNC)) {
        if (file->f_op && file->f_op->fasync)
            file->f_op->fasync(-1, file, 0);
    }
    ima_file_free(file);
    if (file->f_op && file->f_op->release)
        file->f_op->release(inode, file);
    security_file_free(file);
    if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
             !(file->f_mode & FMODE_PATH))) {
        cdev_put(inode->i_cdev);
    }
    fops_put(file->f_op);
    put_pid(file->f_owner.pid);
    if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
        i_readcount_dec(inode);
    if (file->f_mode & FMODE_WRITE)
        drop_file_write_access(file);
    file->f_path.dentry = NULL;
    file->f_path.mnt = NULL;
    file_free(file);
    dput(dentry);
    mntput(mnt);
}

static DEFINE_SPINLOCK(delayed_fput_lock);
static LIST_HEAD(delayed_fput_list);
static void delayed_fput(struct work_struct *unused)
{
    LIST_HEAD(head);
    spin_lock_irq(&delayed_fput_lock);
    list_splice_init(&delayed_fput_list, &head);
    spin_unlock_irq(&delayed_fput_lock);
    while (!list_empty(&head)) {
        struct file *f = list_first_entry(&head, struct file, f_u.fu_list);
        list_del_init(&f->f_u.fu_list);
        __fput(f);
    }
}

static void ____fput(struct callback_head *work)
{
    __fput(container_of(work, struct file, f_u.fu_rcuhead));
}

/*
 * If kernel thread really needs to have the final fput() it has done
 * to complete, call this.  The only user right now is the boot - we
 * *do* need to make sure our writes to binaries on initramfs has
 * not left us with opened struct file waiting for __fput() - execve()
 * won't work without that.  Please, don't add more callers without
 * very good reasons; in particular, never call that with locks
 * held and never call that from a thread that might need to do
 * some work on any kind of umount.
 */
void flush_delayed_fput(void)
{
    delayed_fput(NULL);
}

static DECLARE_WORK(delayed_fput_work, delayed_fput);

void fput(struct file *file)
{
    if (atomic_long_dec_and_test(&file->f_count)) {
        struct task_struct *task = current;
        file_sb_list_del(file);
        if (unlikely(in_interrupt() || task->flags & PF_KTHREAD)) {
            unsigned long flags;
            spin_lock_irqsave(&delayed_fput_lock, flags);
            list_add(&file->f_u.fu_list, &delayed_fput_list);
            schedule_work(&delayed_fput_work);
            spin_unlock_irqrestore(&delayed_fput_lock, flags);
            return;
        }
        init_task_work(&file->f_u.fu_rcuhead, ____fput);
        task_work_add(task, &file->f_u.fu_rcuhead, true);
    }
}

/*
 * synchronous analog of fput(); for kernel threads that might be needed
 * in some umount() (and thus can't use flush_delayed_fput() without
 * risking deadlocks), need to wait for completion of __fput() and know
 * for this specific struct file it won't involve anything that would
 * need them.  Use only if you really need it - at the very least,
 * don't blindly convert fput() by kernel thread to that.
 */
void __fput_sync(struct file *file)
{
    if (atomic_long_dec_and_test(&file->f_count)) {
        struct task_struct *task = current;
        file_sb_list_del(file);
        BUG_ON(!(task->flags & PF_KTHREAD));
        __fput(file);
    }
}

EXPORT_SYMBOL(fput);

void put_filp(struct file *file)
{
    if (atomic_long_dec_and_test(&file->f_count)) {
        security_file_free(file);
        file_sb_list_del(file);
        file_free(file);
    }
}

static inline int file_list_cpu(struct file *file)
{
#ifdef CONFIG_SMP
    return file->f_sb_list_cpu;
#else
    return smp_processor_id();
#endif
}

/* helper for file_sb_list_add to reduce ifdefs */
static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
{
    struct list_head *list;
#ifdef CONFIG_SMP
    int cpu;
    cpu = smp_processor_id();
    file->f_sb_list_cpu = cpu;
    list = per_cpu_ptr(sb->s_files, cpu);
#else
    list = &sb->s_files;
#endif
    list_add(&file->f_u.fu_list, list);
}

void file_sb_list_add(struct file *file, struct super_block *sb)
{
    lg_local_lock(&files_lglock);
    __file_sb_list_add(file, sb);
    lg_local_unlock(&files_lglock);
}

void file_sb_list_del(struct file *file)
{
    if (!list_empty(&file->f_u.fu_list)) {
        lg_local_lock_cpu(&files_lglock, file_list_cpu(file));
        list_del_init(&file->f_u.fu_list);
        lg_local_unlock_cpu(&files_lglock, file_list_cpu(file));
    }
}

#ifdef CONFIG_SMP

/*
 * These macros iterate all files on all CPUs for a given superblock.
 * files_lglock must be held globally.
 */
#define do_file_list_for_each_entry(__sb, __file)       \
{                               \
    int i;                          \
    for_each_possible_cpu(i) {              \
        struct list_head *list;             \
        list = per_cpu_ptr((__sb)->s_files, i);     \
        list_for_each_entry((__file), list, f_u.fu_list)

#define while_file_list_for_each_entry              \
    }                           \
}

#else

#define do_file_list_for_each_entry(__sb, __file)       \
{                               \
    struct list_head *list;                 \
    list = &(sb)->s_files;                  \
    list_for_each_entry((__file), list, f_u.fu_list)

#define while_file_list_for_each_entry              \
}

#endif

void mark_files_ro(struct super_block *sb)
{
    struct file *f;

    lg_global_lock(&files_lglock);
    do_file_list_for_each_entry(sb, f) {
        if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
               continue;
        if (!file_count(f))
            continue;
        if (!(f->f_mode & FMODE_WRITE))
            continue;
        spin_lock(&f->f_lock);
        f->f_mode &= ~FMODE_WRITE;
        spin_unlock(&f->f_lock);
        if (file_check_writeable(f) != 0)
            continue;
        file_release_write(f);
        mnt_drop_write_file(f);
    } while_file_list_for_each_entry;
    lg_global_unlock(&files_lglock);
}

void __init files_init(unsigned long mempages)
{ 
    unsigned long n;

    filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
            SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);

    /*
     * One file with associated inode and dcache is very roughly 1K.
     * Per default don't use more than 10% of our memory for files. 
     */ 

    n = (mempages * (PAGE_SIZE / 1024)) / 10;
    files_stat.max_files = max_t(unsigned long, n, NR_FILE);
    files_defer_init();
    lg_lock_init(&files_lglock, "files_lglock");
    percpu_counter_init(&nr_files, 0);
}